Search

Sanitizing railway stations is a relevant issue especially due to the recent evolution of the Covid-19 pandemic. In this work, we propose a multi-robot approach to sanitize railway stations based on a distributed Deep Q-Learning technique. The framework relies on anonymous information from existing WiFi networks to localize passengers inside the station and to develop a map of possible risky areas to be sanitized. Starting from this map, a swarm of cleaning robots, each one endowed with a robot-specific convolutional neural network, learns how to on-line cooperate inside the station in order to maximize the sanitized area depending on the presence of the passengers.

We present and discuss a human-robot collaboration system suitable for supervising the execution of structured manipulation tasks in industrial assembly scenarios. As a case study, we consider the application domain proposed in the context of the project (PON R& I 2014-2020) ICOSAF (Integrated collaborative systems for Smart Factory) in which a human operator physically interacts with a collaborative robot (Cobot) to perform multiple item insertion tasks in a shared workspace. The proposed system combines hierarchical task orchestration and human intention recognition during human-robot interaction through hand-guidance. We provide an overview of the system discussing an initial experimental evaluation.

We present the control architecture of a modular robotic system designed for hospital logistics. The robotics system is an automated guided vehicle that can autonomously perform tasks like carrying and delivering objects, medicines or devices, while interacting with humans in the hospital environment. Specifically, the robotic platform is designed to dock and move passive vehicles (like carts, containers, etc.), which dynamically change the robot shape and function during the task execution. We describe the overall control architecture focusing on the executive and the planning systems. We discuss the system at work in different scenarios considering both autonomous and interactive tasks.

In social and service robotics, complex collaborative tasks are expected to be executed while interacting with humans in a natural and fluent manner. In this scenario, the robotic system is typically provided with structured tasks to be accomplished, but must also continuously adapt to human activities, commands, and interventions. We propose to tackle these issues by exploiting the concept of cognitive control, introduced in cognitive psychology and neuroscience to describe the executive mechanisms needed to support adaptive responses and complex goal-directed behaviors. Specifically, we rely on a supervisory attentional system to orchestrate the execution of hierarchically organized robotic behaviors. This paradigm seems particularly effective not only for flexible plan execution but also for human–robot interaction, because it directly provides attention mechanisms considered as pivotal for implicit, non-verbal human–human communication. Following this approach, we are currently developing a robotic cognitive control framework enabling collaborative task execution and incremental task learning. In this paper, we provide a uniform overview of the framework illustrating its main features and discussing the potential of the supervisory attentional system paradigm in different scenarios where humans and robots have to collaborate for learning and executing everyday activities.

Automatic depalletizing is becoming a practice widely applied in warehouses to automatize and speed-up logistics. On the other hand, the necessity to adapt the preexisting logistic lines to a custom automatic system can be a limit for the application of robotic solutions into smaller facilities like supermarkets. In this work, we tackle this issue by proposing a flexible and adaptive gripper for robotic depalletizing. The gripper is designed to be assembled on the end-tip of an industrial robotic arm. A novel patent-pending mechanism allows grasping boxes and products from both the upper and the lateral side enabling the depalletizing of boxes with complex shape. Moreover, the gripper is reconfigurable with five actuated degrees of freedom, that are automatically controlled using the embedded sensors to adapt grasping to different shapes and weights.

We evaluated the 3-year drug survival and efficacy of the biosimilar SB4/Benepali in rheumatoid arthritis (RA), psoriatic arthritis (PsA) and ankylosing spondylitis (AS) patients, previously treated with etanercept (ETA). Drug survival rate was calculated using the Kaplan–Meier method and Cox proportional hazard models were developed to examine predictors of SB4 discontinuation. 236 patients (120 RA, 80 PsA and 36 AS), aged 60.7 ± 13.8 years and with an ETA duration of 4.1 ± 3.4 years were included. The 3-year retention rate for SB4 was 94.4%, 88% and 86% in AS, RA and PsA patients, respectively, with no difference between groups. Patients without comorbid disease had higher retention rates vs. patients with comorbid disease (90% vs. 60%, p < 0.0001). Disease activity, as measured by DAS28, DAPSA and BASDAI remained stable over the 3 years. Comorbid disease (hazard ratio; HR: 4.06, p < 0.0001) and HAQ at baseline (HR: 2.42, p = 0.0024) significantly increased the risk of SB4 discontinuation, while previous ETA duration was negatively associated with SB4 discontinuation (HR: 0.97, p = 0.0064). Forty-one (17.4%) patients left the study due to the interruption of the SB4 treatment, 31 (75.6%) discontinued due to inefficacy and 10 (24.4%) due to adverse events. This real-life study confirms the similar efficacy profile of ETA with long-term retention and a good safety profile in inflammatory arthritis patients.

Task and motion planning in robotics are typically addressed by separated intertwined methods. Task planners generate abstract high-level actions to be executed, while motion planners provide the associated discrete movements in the configuration space satisfying kinodynamic constraints. However, these two planning processes are strictly dependent, therefore the problem of combining task and motion planning with a uniform approach is very relevant. In this work, we tackle this issue by proposing a RRT-based method that addresses combined task and motion planning. Our approach relies on a combined metric space where both symbolic (task) and sub-symbolic (motion) spaces are represented. The associated notion of distance is then exploited by a RRT-based planner to generate a plan that includes both symbolic actions and feasible movements in the configuration space. The proposed method is assessed in several case studies provided by a real-world hospital logistic scenario, where an omni-directional mobile robot is involved in navigation and transportation tasks.

Combined task and motion planning is a relevant issue in robotics. In path and motion planning, Rapidly-exploring Random Trees (RRTs) have been proposed as effective methods to efficiently search high-dimensional spaces. On the other hand, the deployment of these techniques to symbolic task planning problems has been partially investigated. In this paper, we explore this issue proposing a method to combine task and motion planning based on RRTs. Our approach relies on a metric space where both symbolic (task) and sub-symbolic (motion) spaces are represented. The associated notion of distance is then exploited by a RRT-based planner to generate a plan that includes both symbolic actions and obstacle-free trajectories. The proposed method is assessed in several case studies provided by a real-world hospital logistic scenario, where an omni-directional mobile robot is involved in pick-carry-and-place tasks.

The ability to explain and motivate the execution of actions is a key feature for complex robotic systems. In this paper, we propose an executive framework, endowed with a hierarchical representation of tasks, where robot actions and constraints can be directly associated with natural language explanations in order to facilitate the design of novel tasks and the understanding of executing ones. The executive system relies on a cognitive control paradigm where attentional regulations are exploited to both schedule and explain robotic activities during tasks execution. The framework has been deployed in an industrial scenario where multiple pick-carry-and-place tasks are to executed, showing how the proposed approach naturally supports explainability and legibility of the robot behaviors.

Integrating a robotic system into the depalletizing process of a supermarket demands a high level of autonomy, based on strong perceptive capabilities. This letter presents a system for detection, recognition, and localization of heterogeneous cases in a depalletizing robotic cell, using a single RGB-D camera. Such a system integrates apriori information on the content of the pallet with data from the RGB-D camera, exploiting a sequence of 2D and 3D model-based computer-vision algorithms. The effectiveness of the proposed methodology is assessed in an experiment where multiple cases and pallet configurations are considered. Finally, a complete depalletizing process is shown.

Cobots (Collaborative robots) are increasingly employed in industrial workplaces, assisting human operators in decreasing the weight and the repetitiveness of their activities. In order to promote the acceptance of cobots, novel interaction paradigms enabling intuitive collaboration between humans and robots are needed. In this work, we propose a variable admittance control framework based on virtual fixtures, in which the damping and the stiffness of the admittance controller are on-line adjusted to increase the effectiveness of the co-manipulation task. Virtual paths are generated to support and guide the operator during collaborative task execution, providing him/her an over-responsive compliant system when the robot is far from the targets and a precise heavy tool in their proximity. The proposed approach has been compared with a fixed admittance controller in an industrial use case consisting of a human operator interacting with a Kuka LBR IIWA arm. The collected results demonstrate the effectiveness of the proposed approach.

Learning everyday tasks from human demonstrations requires unsupervised segmentation of seamless demonstrations, which may result in highly fragmented and widely spread symbolic representations. Since the time needed to plan the task depends on the amount of possible behaviors, it is preferable to keep the number of behaviors as low as possible. In this work, we present an approach to simplify the symbolic representation of a learned task which leads to a reduction of the number of possible behaviors. The simplification is achieved by merging sequential behaviors, i.e. behaviors which are logically sequential and act on the same object. Assuming that the task at hand is encoded in a rooted tree, the approach traverses the tree searching for sequential nodes (behaviors) to merge. Using simple rules to assign pre- and post-conditions to each node, our approach significantly reduces the number of nodes, while keeping unaltered the task flexibility and avoiding perceptual aliasing. Experiments on automatically generated and learned tasks show a significant reduction of the planning time.

In this work, we present an approach to imitation learning and flexible execution of dual-arm structured tasks. The proposed framework exploits imitation learning and attentional supervision to learn both a set of motion primitives and the associated tasks structure. During the teaching phase, attentional supervision allows the teacher to exploit attention manipulation, like object and verbal cueing, to facilitate the demonstration. In this phase, motion data are automatically segmented, annotated and learned in a compact form for on-line motion generation. During the execution phase, the learned task structure is exploited to synchronize left and right arm movements and to adapt task execution to the operative context. The proposed approach is demonstrated in a simulated kitchen scenario considering a pizza preparation task.